فهم الصور

from google import genai

client = genai.Client()

uploaded_file = client.files.upload(file="path/to/organ.jpg")

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "text", "text": "Caption this image."},
        {
            "type": "image",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        }
    ]
)
print(interaction.steps[-1].content[0].text)

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

const uploadedFile = await client.files.upload({
    file: "path/to/organ.jpg",
    config: { mimeType: "image/jpeg" }
});

const interaction = await client.interactions.create({
    model: "gemini-3-flash-preview",
    input: [
        {type: "text", text: "Caption this image."},
        {
            type: "image",
            uri: uploadedFile.uri,
            mimeType: uploadedFile.mimeType
        }
    ]
});
console.log(interaction.steps.at(-1).content[0].text);

# First upload the file using the Files API, then use the URI:
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": [
      {"type": "text", "text": "Caption this image."},
      {
        "type": "image",
        "uri": "YOUR_FILE_URI",
        "mime_type": "image/jpeg"
      }
    ]
  }'

from google import genai

with open('path/to/small-sample.jpg', 'rb') as f:
    image_bytes = f.read()

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "text", "text": "Caption this image."},
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/jpeg"
        }
    ]
)
print(interaction.steps[-1].content[0].text)

import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";

const client = new GoogleGenAI({});
const base64ImageFile = fs.readFileSync("path/to/small-sample.jpg", {
  encoding: "base64",
});

const interaction = await client.interactions.create({
    model: "gemini-3-flash-preview",
    input: [
        {type: "text", text: "Caption this image."},
        {
            type: "image",
            data: base64ImageFile,
            mime_type: "image/jpeg"
        }
    ]
});
console.log(interaction.steps.at(-1).content[0].text);

IMG_PATH="/path/to/your/image1.jpg"

if [[ "$(base64 --version 2>&1)" = *"FreeBSD"* ]]; then
  B64FLAGS="--input"
else
  B64FLAGS="-w0"
fi

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": [
      {"type": "text", "text": "Caption this image."},
      {
        "type": "image",
        "data": "'"$(base64 $B64FLAGS $IMG_PATH)"'",
        "mime_type": "image/jpeg"
      }
    ]
  }'

from google import genai

client = genai.Client()

my_file = client.files.upload(file="path/to/sample.jpg")

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "text", "text": "Caption this image."},
        {
            "type": "image",
            "uri": my_file.uri,
            "mime_type": my_file.mime_type
        }
    ]
)
print(interaction.steps[-1].content[0].text)

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

const myfile = await client.files.upload({
    file: "path/to/sample.jpg",
    config: { mimeType: "image/jpeg" },
});

const interaction = await client.interactions.create({
    model: "gemini-3-flash-preview",
    input: [
        {type: "text", text: "Caption this image."},
        {
            type: "image",
            uri: myfile.uri,
            mime_type: myfile.mimeType
        }
    ]
});
console.log(interaction.steps.at(-1).content[0].text);

# First upload the file (see Files API guide for details)
# Then use the file URI in the request:

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": [
      {"type": "text", "text": "Caption this image."},
      {
        "type": "image",
        "uri": "YOUR_FILE_URI",
        "mime_type": "image/jpeg"
      }
    ]
  }'

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "text", "text": "What is different between these two images?"},
        {
            "type": "image",
            "uri": "https://example.com/image1.jpg",
            "mime_type": "image/jpeg"
        },
        {
            "type": "image",
            "uri": "https://example.com/image2.jpg",
            "mime_type": "image/jpeg"
        }
    ]
)
print(interaction.steps[-1].content[0].text)

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    model: "gemini-3-flash-preview",
    input: [
        {type: "text", text: "What is different between these two images?"},
        {
            type: "image",
            uri: "https://example.com/image1.jpg",
            mime_type: "image/jpeg"
        },
        {
            type: "image",
            uri: "https://example.com/image2.jpg",
            mime_type: "image/jpeg"
        }
    ]
});
console.log(interaction.steps.at(-1).content[0].text);

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": [
      {"type": "text", "text": "What is different between these two images?"},
      {
        "type": "image",
        "uri": "https://example.com/image1.jpg",
        "mime_type": "image/jpeg"
      },
      {
        "type": "image",
        "uri": "https://example.com/image2.jpg",
        "mime_type": "image/jpeg"
      }
    ]
  }'

from google import genai
from PIL import Image
import json

client = genai.Client()
prompt = "Detect the all of the prominent items in the image. The box_2d should be [ymin, xmin, ymax, xmax] normalized to 0-1000."

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "text", "text": prompt},
        {
            "type": "image",
            "uri": "https://example.com/image.png",
            "mime_type": "image/png"
        }
    ],
    response_format={
        "type": "text",
        "mime_type": "application/json"
    }
)

bounding_boxes = json.loads(interaction.steps[-1].content[0].text)
print("Bounding boxes:", bounding_boxes)

from google import genai
from PIL import Image
import json

client = genai.Client()

prompt = """
Give the segmentation masks for the wooden and glass items.
Output a JSON list of segmentation masks where each entry contains the 2D
bounding box in the key "box_2d", the segmentation mask in key "mask", and
the text label in the key "label". Use descriptive labels.
"""

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "text", "text": prompt},
        {
            "type": "image",
            "uri": "https://example.com/image.png",
            "mime_type": "image/png"
        }
    ],
    config={
        "thinking_level": "minimal"  # Minimize thinking for better detection results
    }
)

items = json.loads(interaction.steps[-1].content[0].text)
print("Segmentation results:", items)